Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific mentions of academic journals, publishers, and institutions, particularly focusing on names and locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political events and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apologise
    -0.83
     organis
    -0.74
     realise
    -0.72
    Firstly
    -0.72
     Firstly
    -0.69
     analyse
    -0.65
     recognise
    -0.65
     organising
    -0.63
     centres
    -0.63
     realised
    -0.62
    POSITIVE LOGITS
    ]).
    0.72
    }.
    0.72
    .).
    0.71
    )).
    0.66
     attRot
    0.65
     afterward
    0.64
    >.
    0.64
    ]),
    0.63
    asio
    0.62
    .]
    0.62
    Act Density 1.270%

    No Known Activations